Applied AI Engineer

Role Summary

Own the 0 to 1. You'll turn vague customer use cases into working proofs-of-concept that showcase what Mem0 can do. This means rapid full-stack prototyping, stitching together AI tools, and aggressively experimenting with memory retrieval approaches until the use case works end-to-end. You'll partner closely with Research and Backend, communicate trade-offs clearly, and hand off winning prototypes that can be hardened for production.

You'll be one of the first Applied AI hires, working directly with the founders and a small research + backend team.

What You'll Ship Early

• First 30 days: Build and demo a working POC for a real customer use case. UI, APIs, data pipeline, Mem0 integration, end-to-end.
• First 60 days: Own two to three active POC workstreams, establish eval harnesses, and develop a repeatable playbook for turning customer problems into Mem0-powered demos.
• First 90 days: Be the go-to person for applied prototyping at Mem0. You'll have shipped multiple demos, contributed retrieval improvements back to the core product, and built templates that accelerate future POCs.

What You'll Do

• Build POCs for real use cases. Stand up end-to-end demos (UI + APIs + data) that integrate Mem0 in the customer's flow.
• Experiment with memory retrieval. Try different embeddings, indexing, hybrid search, re-ranking, chunking/windowing, prompts, and caching to hit task-level quality and latency targets.
• Prototype with Research. Implement paper ideas and new techniques from scratch, compare baselines, and keep what wins.
• Create eval harnesses. Define small gold sets and lightweight metrics to judge POC success; instrument demos with basic telemetry.
• Integrate AI tooling. Combine LLMs, vector DBs, Mem0 SDKs/APIs, and third-party services into coherent workflows.
• Collaborate tightly. Work with Backend on clean contracts and data models; with Research on hypotheses; share learnings and next steps.
• Package and handoff. Write concise docs, scripts, and templates so Engineering can productionize quickly.

Minimum Qualifications

• Full-stack fluency. Next.js/React on the front end and Python backends (FastAPI/Django/Flask) or Node where needed.
• Strong Python and TypeScript/JavaScript. Comfortable building APIs, wiring data models, and deploying quick demos.
• Hands-on with the LLM/RAG stack. Embeddings, vector databases, retrieval strategies, prompt engineering.
• Track record of rapid prototyping. Moving from idea to demo in days, not months. Clear documentation of results and trade-offs.
• Ability to design small, meaningful evaluations for a use case (quality + latency) and iterate based on evidence.
• Excellent communication with Research and Backend. Crisp specs, readable code, and honest status updates.

Nice to Have

• Model serving/fine-tuning experience (vLLM, LoRA/PEFT) and lightweight batch/async pipelines.
• Deployments on Vercel/serverless, Docker, basic k8s familiarity. CI for demo apps.
• Data visualization and UX polish for compelling demos.
• Prior Forward-Deployed/Solutions/Prototyping role turning customer needs into working software.

Compensation

• Salary: $150K to $250K base (depending on experience)
• Equity: 0.10% to 0.50%
• Location: San Francisco (in-person)

About Mem0

We're building the memory layer for AI agents. Long-term memory that lets AI remember conversations, learn from interactions, and build context over time. We already power millions of memory operations daily across companies building AI-native products.

Mem0 is a Y Combinator (S24) company, backed by top-tier investors including Peak XV and Basis Set Ventures. We raised $24M to make this the default memory infrastructure for AI.

The Founders

Deshraj Yadav, Co-founder and CTO. Led the AI Platform at Tesla Autopilot, enabling large-scale training, model evaluation, and observability for Tesla's full self-driving development. MS in CS from Georgia Tech (ML specialization). Created EvalAI as his master's thesis, an open-source ML evaluation platform used by researchers at CMU, Stanford, Facebook, and Google. Published at CVPR, ECCV, AAAI.

Taranjeet Singh, Co-founder and CEO. Started as a software engineer at Paytm, then built an AI-powered tutoring app at Gradeup (acquired by Byju's) that was featured at Google I/O. Joined Khatabook (YC S18) as first growth engineer and became Senior PM. Built cookup.ai, the first GPT app store, and scaled it to 1M+ users with zero marketing spend. Co-authored an O'Reilly book chapter on industrial NLP alongside researchers from Google AI, CMU, and Microsoft Research.

Together, Deshraj and Taranjeet co-created EvalAI and later built Embedchain, an open-source RAG framework with 2M+ downloads. While building Embedchain, they saw firsthand how LLMs forget everything between sessions, leading to repetitive, impersonal interactions. Mem0 was born to fix that: a hybrid memory architecture combining graph, vector, and key-value stores that makes AI applications stateful, personalized, and cost-efficient.

How We Work

• Office-first in SF. Hallway chats, whiteboard sessions, and shared meals. The best ideas happen in person.
• Velocity with craftsmanship. We ship fast but build for the long term. Every system needs to be fast, reliable, and elegant.
• We debug retrieval quality over lunch. Half our Slack is embedding comparisons. If you've ever argued about chunk sizes at 11pm, you'll fit right in.
• Data-driven, not ego-driven. The best solution wins, whether it comes from a founder or an engineer who joined yesterday. Results and metrics guide decisions.
• Small team, big leverage. You'll work directly with the founders and a tight research + backend team. No layers, no committees.